[VP][DAGCombine] Use `simplifySelect` when combining vp.select. (#87342)

Hi all,

This patch is a follow-up of #79101. It migrates logic from
`visitVSELECT` to `visitVP_SELECT` to simplify `vp.select`. With this
patch we can do the following combinations:

```
vp.select undef, T, F --> T (if T is a constant), F otherwise
vp.select <condition>, undef, F --> F
vp.select <condition>, T, undef --> T
vp.select false, T, F --> F
vp.select <condition>, T, T --> T
```

I'm a total newbie to llvm and I'm sure there's room for improvements in
this patch. Please let me know if you have any advice. Thank you in
advance!

2 files changed, 60 insertions, 0 deletions

diff --git a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
index 2f46b23..b889e4f 100644
--- a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -12056,6 +12056,13 @@ SDValue DAGCombiner::foldVSelectOfConstants(SDNode *N) {
 }
 
 SDValue DAGCombiner::visitVP_SELECT(SDNode *N) {
+  SDValue N0 = N->getOperand(0);
+  SDValue N1 = N->getOperand(1);
+  SDValue N2 = N->getOperand(2);
+
+  if (SDValue V = DAG.simplifySelect(N0, N1, N2))
+    return V;
+
   if (SDValue V = foldBoolSelectToLogic<VPMatchContext>(N, DAG))
     return V;
 
diff --git a/llvm/test/CodeGen/RISCV/rvv/vselect-vp.ll b/llvm/test/CodeGen/RISCV/rvv/vselect-vp.ll
index 0d52dd7..0a5e501 100644
--- a/llvm/test/CodeGen/RISCV/rvv/vselect-vp.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/vselect-vp.ll
@@ -825,3 +825,56 @@ define <vscale x 2 x i1> @select_cond_x_cond(<vscale x 2 x i1> %x, <vscale x 2 x
   %a = call <vscale x 2 x i1> @llvm.vp.select.nxv2i1(<vscale x 2 x i1> %x, <vscale x 2 x i1> %y, <vscale x 2 x i1> %x, i32 %evl)
   ret <vscale x 2 x i1> %a
 }
+
+define <vscale x 2 x i1> @select_undef_T_F(<vscale x 2 x i1> %x, <vscale x 2 x i1> %y, i32 zeroext %evl) {
+; CHECK-LABEL: select_undef_T_F:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vmv1r.v v0, v8
+; CHECK-NEXT:    ret
+  %a = call <vscale x 2 x i1> @llvm.vp.select.nxv2i1(<vscale x 2 x i1> poison, <vscale x 2 x i1> %x, <vscale x 2 x i1> %y, i32 %evl)
+  ret <vscale x 2 x i1> %a
+}
+
+define <vscale x 2 x i1> @select_undef_undef_F(<vscale x 2 x i1> %x, i32 zeroext %evl) {
+; CHECK-LABEL: select_undef_undef_F:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    ret
+  %a = call <vscale x 2 x i1> @llvm.vp.select.nxv2i1(<vscale x 2 x i1> poison, <vscale x 2 x i1> undef, <vscale x 2 x i1> %x, i32 %evl)
+  ret <vscale x 2 x i1> %a
+}
+
+define <vscale x 2 x i1> @select_unknown_undef_F(<vscale x 2 x i1> %x, <vscale x 2 x i1> %y, i32 zeroext %evl) {
+; CHECK-LABEL: select_unknown_undef_F:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vmv1r.v v0, v8
+; CHECK-NEXT:    ret
+  %a = call <vscale x 2 x i1> @llvm.vp.select.nxv2i1(<vscale x 2 x i1> %x, <vscale x 2 x i1> undef, <vscale x 2 x i1> %y, i32 %evl)
+  ret <vscale x 2 x i1> %a
+}
+
+define <vscale x 2 x i1> @select_unknown_T_undef(<vscale x 2 x i1> %x, <vscale x 2 x i1> %y, i32 zeroext %evl) {
+; CHECK-LABEL: select_unknown_T_undef:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vmv1r.v v0, v8
+; CHECK-NEXT:    ret
+  %a = call <vscale x 2 x i1> @llvm.vp.select.nxv2i1(<vscale x 2 x i1> %x, <vscale x 2 x i1> %y, <vscale x 2 x i1> poison, i32 %evl)
+  ret <vscale x 2 x i1> %a
+}
+
+define <vscale x 2 x i1> @select_false_T_F(<vscale x 2 x i1> %x, <vscale x 2 x i1> %y, <vscale x 2 x i1> %z, i32 zeroext %evl) {
+; CHECK-LABEL: select_false_T_F:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vmv1r.v v0, v9
+; CHECK-NEXT:    ret
+  %a = call <vscale x 2 x i1> @llvm.vp.select.nxv2i1(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i1> %y, <vscale x 2 x i1> %z, i32 %evl)
+  ret <vscale x 2 x i1> %a
+}
+
+define <vscale x 2 x i1> @select_unknown_T_T(<vscale x 2 x i1> %x, <vscale x 2 x i1> %y, i32 zeroext %evl) {
+; CHECK-LABEL: select_unknown_T_T:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vmv1r.v v0, v8
+; CHECK-NEXT:    ret
+  %a = call <vscale x 2 x i1> @llvm.vp.select.nxv2i1(<vscale x 2 x i1> %x, <vscale x 2 x i1> %y, <vscale x 2 x i1> %y, i32 %evl)
+  ret <vscale x 2 x i1> %a
+}